Native UNet for Stable Diffusion
Description
Native R torch implementation of UNet2DConditionModel. Replaces TorchScript for better GPU compatibility.
Usage
unet_native(in_channels = 4L, out_channels = 4L,
block_out_channels = c(320L, 640L, 1280L, 1280L),
layers_per_block = 2L, cross_attention_dim = 1024L,
attention_head_dim = 64L)
Arguments
in_channels: Input channels (default 4 for latent space)out_channels: Output channels (default 4)block_out_channels: Channel multipliers per blocklayers_per_block: Number of ResBlocks per down/up blockcross_attention_dim: Context dimension from text encoderattention_head_dim: Dimension per attention head
Value
An nn_module representing the UNet